Attention-Based Models for Speech Recognition

By Jan Chorowski, Dzmitry Bahdanau, Dmitriy Serdyuk, Kyunghyun Cho, Yoshua Bengio. 2015

2,769 citations recorded by the source corpus.

Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks including machine translation, handwriting synthesis [1,2] and image caption generation [3]. We extend the attention-mechanism with features needed for speech recognition. We show that while an adaptation of the model used for machine translation in [2] reaches a competitive 18.7% phoneme error rate (PER) on the TIMET phoneme recognition task, it can only be applied to utterances which are roughly as long as the ones it was trained on. We offer a qualitative explanation of this failure and propose a novel and generic method of adding location-awareness to the attention mechanism to alleviate this issue. The new method yields a model that is robust to long inputs and achieves 18% PER in single utterances and 20% in 10-times longer (repeated) utterances. Finally, we propose a change to the attention mechanism that prevents it from concentrating too much on single frames, which further reduces PER to 17.6% level.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Yoshua Bengio
  2. Mohit Bansal
  3. Jianfeng Gao
  4. Quoc V. Le
  5. Percy Liang
  6. Kyunghyun Cho
  7. Luke S. Zettlemoyer
  8. Graham Neubig

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Xiaogang Wang
  4. Trevor Darrell
  5. Ming-Hsuan Yang
  6. Andrew Zisserman
  7. Yi Yang
  8. Jitendra Malik

In Speech & Audio

  1. Jinyu Li
  2. Shinji Watanabe
  3. Yu Zhang
  4. Wei-Ning Hsu
  5. Hung-yi Lee
  6. Dong Yu
  7. Xu Tan
  8. James R. Glass

Citations in the corpus